<!DOCTYPE html>
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
</head>
<body>
<p><span class="HwtZe" lang="en"><span class="jCAhz ChMk0b"><span
class="ryNqvb">It is necessary to disable THP so often that
I had to write a script for this purpose.</span></span> <span
class="jCAhz ChMk0b"><span class="ryNqvb">Doing this using the
service is much more convenient than doing it any other way,
in my opinion.</span></span></span></p>
<p><span class="HwtZe" lang="en"><span class="jCAhz ChMk0b"><span
class="ryNqvb"><a class="moz-txt-link-freetext" href="https://github.com/yvoinov/memory-tools/blob/main/disable_thp.sh">https://github.com/yvoinov/memory-tools/blob/main/disable_thp.sh</a><br>
</span></span></span></p>
<div class="moz-cite-prefix">16.03.2024 14:23, Tarko Tikan via
Unbound-users пишет:<br>
</div>
<blockquote type="cite"
cite="mid:594fb6f6-ac15-40d1-bc23-0a69e4f86652@lanparty.ee">hey,
<br>
<br>
<blockquote type="cite">The question is that stats metrics (mem*)
are stable . They rapidly grow after startup and stay at a
logical
<br>
maximum and don't keep growing.
<br>
<br>
But the process size does.
<br>
</blockquote>
<br>
We saw the same on Debian due to THP like Oliver already
mentioned. See <a class="moz-txt-link-freetext" href="https://github.com/NLnetLabs/unbound/issues/724">https://github.com/NLnetLabs/unbound/issues/724</a>
<br>
<br>
We "solved" this by disabling THP on our unbound machines.
<br>
<br>
</blockquote>
</body>
</html>